Robustness of the BYM model in absence of spatial variation in the residuals.

Abstract : ABSTRACT: BACKGROUND: In the context of ecological studies, the Bayesian hierarchical Poisson model is of prime interest when studying the association between environmental exposure and rare diseases. However, adding spatially structured extra-variability in the model fitted to the data when such extra-variability does not exist conditionally on the covariates included in the model (over-fitting ) may bias the estimation of the ecological association between covariates and relative risks toward the null. In order to investigate that possibility, a simulation study of the impact of introducing unnecessary residual spatial structure in the estimation model was conducted. RESULTS: In the case where no underlying extra-variability from the Poisson process exists, the simulation results show that models accounting for structured and unstructured residuals do not underestimate the ecological association, unless covariates have a very strong autocorrelation structure, i.e., 0.98 at 100 km on a territory of diameter 1000 km.
Type de document :
Article dans une revue
International Journal of Health Geographics, BioMed Central, 2007, 6 (1), pp.39. <10.1186/1476-072X-6-39>
Liste complète des métadonnées


http://www.hal.inserm.fr/inserm-00174861
Contributeur : U754 Secretariat <>
Soumis le : mardi 25 septembre 2007 - 16:15:58
Dernière modification le : mercredi 4 janvier 2017 - 16:22:57
Document(s) archivé(s) le : jeudi 8 avril 2010 - 22:12:23

Identifiants

Collections

Citation

Aurélien Latouche, Chantal Guihenneuc-Jouyaux, Claire Girard, Denis Hémon. Robustness of the BYM model in absence of spatial variation in the residuals.. International Journal of Health Geographics, BioMed Central, 2007, 6 (1), pp.39. <10.1186/1476-072X-6-39>. <inserm-00174861>

Partager

Métriques

Consultations de
la notice

112

Téléchargements du document

137